Model risks Threats, Tactics, and Defenses: Field Guide
RCCE students will learn machine learning model security risks including adversarial attacks, model poisoning, model theft, model inversion, and membership inference attacks. RCCE students will learn to assess ML model security throughout the model lifecycle from training through deployment, identify vulnerabilities in model architectures and training pipelines, detect adversarial input attacks designed to cause misclassification, prevent model poisoning through training data integrity controls, protect model intellectual property against extraction attacks, implement model monitoring for drift and adversarial behavior, and develop incident response procedures for compromised ML models. This threat-focused course teaches students to think like adversaries while building robust defenses. Starting from foundational concepts, RCCE students will learn to analyze attack techniques, build detection logic, and implement defensive strategies that proactively identify threats before they cause damage. Students develop a threat-informed mindset that drives better security decisions across all operational activities.
- Security Engineers building defensive controls
- Security Analysts and Blue Team members
- Systems Administrators with security responsibilities
- GRC and Risk Professionals supporting controls
- Professionals implementing Model risks Threats, Tactics, and Defenses: Field Guide
- Design a scalable privilege management architecture with policy and enforcement
- Explain Course Overview fundamentals
- Execute hands-on tasks for what you will learn — covering ML model security risk landscape.
- Execute hands-on tasks for skills you will gain — covering ML security across lifecycle.
- Execute hands-on tasks for threat-informed mindset — covering Think like an adversary to build robust defenses.
- Execute hands-on tasks for the ml security landscape
- Execute hands-on tasks for adversarial attacks
- Design a scalable privilege management architecture with policy and enforcement, including Crafted inputs cause, Corrupt training data or process, and Extract model via query access.
- Execute hands-on tasks for supply chain risks — covering Reconstruct training data.
- Execute hands-on tasks for attack surfaces at each phase — covering Data Collection — poisoning, label flipping, data injection.
| Module 01 | Model Risks: Threats, Tactics, |
| Module 02 | Course Overview |
| Module 03 | What You Will Learn |
| Module 04 | Skills You Will Gain |
| Module 05 | Threat-Informed Mindset |
| Module 06 | The ML Security Landscape |
| Module 07 | Adversarial Attacks |
| Module 08 | Model Poisoning |
| Module 09 | Model Theft |
| Module 10 | Supply Chain Risks |
| Module 11 | ML Model Lifecycle Security |
| Module 12 | Attack Surfaces at Each Phase |
| Module 13 | Adversarial Attack Fundamentals |
| Module 14 | Core Concept |
All hands-on labs run on Rocheston Rose X OS. Students practice model risks threats, tactics, and defenses: field guide by implementing the controls discussed in class, with a focus on real-world deployment, monitoring, and validation.
- Lab 1: Design a scalable privilege management architecture with policy and enforcement
- Lab 2: Explain Course Overview fundamentals
- Lab 3: Execute hands-on tasks for what you will learn
- Lab 4: Execute hands-on tasks for skills you will gain
- Lab 5: Execute hands-on tasks for threat-informed mindset
Upon successful completion of this course, students will receive an official RCCE Course Completion Certificate for Model risks Threats, Tactics, and Defenses: Field Guide, verifiable through the Rocheston certification portal.
- Full access to all course materials and slide decks
- Hands-on lab access on Rocheston Rose X OS environment
- Access to Rocheston CyberNotes
- Access to Rocheston Zelfire — EDR/XDR SIEM platform
- Access to Rocheston Raven — online cyber range exercise platform
- Access to Rocheston Vulnerability Vines AI